Scholarlink

The ever-growing ocean of available books online and offline can overwhelm even the most dedicated reader. The increasing volume of digital content is leading to a rush in demand for effective recommendation systems that can help users discover relevant and personalized information. This paper presents a comprehensive overview of a book recommendation system built upon machine learning algorithms. The system aims to enhance user experience by providing personalized book recommendation for individual preferences and behavior. The proposed recommendation system works on collaborated filtered method, content driven filter method that approaches to understand the strengths of each method. Collaborative filtering: Depends on user-item interaction and user behavior pattern to identify similarity and recommend book liked by all users with same taste. Content driven filtered approach recommend book depending on the user and the features of those books. Hybrid approaches: Both collaborative and content-based filtering are used for enhanced accuracy and variety in recommendations.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Digital Contents Enabled Personalized Book Recommendation System with Optimized Hyperparameters Tuned Non-parametric Supervised Classification Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ayush Pal,
  • Ditsa Ghosh,
  • Tiansheng Yang,
  • Lu Wang,
  • Bharati Rathore,
  • Hrudaya Kumar Tripathy

摘要

The ever-growing ocean of available books online and offline can overwhelm even the most dedicated reader. The increasing volume of digital content is leading to a rush in demand for effective recommendation systems that can help users discover relevant and personalized information. This paper presents a comprehensive overview of a book recommendation system built upon machine learning algorithms. The system aims to enhance user experience by providing personalized book recommendation for individual preferences and behavior. The proposed recommendation system works on collaborated filtered method, content driven filter method that approaches to understand the strengths of each method. Collaborative filtering: Depends on user-item interaction and user behavior pattern to identify similarity and recommend book liked by all users with same taste. Content driven filtered approach recommend book depending on the user and the features of those books. Hybrid approaches: Both collaborative and content-based filtering are used for enhanced accuracy and variety in recommendations.